Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    occurrences of the letter 'E' in various contexts, indicating a focus on high-frequency letters or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sanitize
    -0.16
    lei
    -0.15
    ieves
    -0.15
     Orient
    -0.15
     CHARSET
    -0.14
    quia
    -0.14
    unders
    -0.14
    иÑĪ
    -0.13
    .githubusercontent
    -0.13
    quila
    -0.13
    POSITIVE LOGITS
    bone
    0.20
    bru
    0.17
    itan
    0.17
    tere
    0.17
    len
    0.16
    lin
    0.16
    rika
    0.16
    unj
    0.15
    merce
    0.15
    ivor
    0.15
    Act Density 0.024%

    No Known Activations